Haoxiang-Wang

ISR

Invariant-feature Subspace Recovery (ISR)

Compositional-Feature-Alignment

Code of Compositional Feature Alignment for Finetuning CLIP and DINOv2

FedADG

Federated Adversarial Domain Generalization

gradual-domain-adaptation

Code for Gradual Domain Adaptation

DeepLearningImplementations

Implementation of recent Deep Learning papers

Bloqade.jl

Package for the quantum computation and quantum simulation based on the neutral-atom architecture.

dev-axolotl

Go ahead and axolotl questions

Gradient_Starvation

Gradient Starvation: A Learning Proclivity in Neural Networks

higher

higher is a pytorch library allowing users to obtain higher order gradients over losses spanning training loops rather than individual training steps.

LMFlow

An Extensible Toolkit for Finetuning and Inference of Large Foundation Models. Large Models for All.

Mixup-Data-Dependency

Code associated with the paper "Towards Understanding the Data Dependency of Mixup-style Training".

models

Models built with TensorFlow

neural-tangents

Fast and Easy Infinite Neural Networks in Python

reward-bench

RewardBench: the first evaluation tool for reward models.

tensorboard-aggregator

Aggregate multiple tensorboard runs to new summary or csv files

tensorflow

Computation using data flow graphs for scalable machine learning

UIUC-CS225

Machine problems for UIUC data structures

wise-ft

write-rnn-tensorflow

Generative Handwriting using LSTM Mixture Density Network with TensorFlow